Mask R-CNN assisted diagnosis of spinal tuberculosis

Wenjun Li, Yanfan Li, Huan Peng, Yongjie Yang, Weijun Liang

Abstract: The risk of spinal tuberculosis (ST) is particularly high in underdeveloped regions with inadequate medical conditions. This not only leads to misdiagnosis and delays in treatment progress but also contributes to the continued transmission of tuberculosis bacteria, posing a risk to other individuals. Currently, CT imaging is extensively utilized in computer-aided diagnosis (CAD). However, manual diagnosis by doctors may result in subjective judgments and misdiagnosis. Therefore, an accurate and objective method is needed for the diagnosis of spinal tuberculosis. In this paper, we put forward an assistive diagnostic approach for spinal tuberculosis that is based on deep learning. The approach leverages the Mask-RCNN model. Moreover, we modify the original model network by incorporating cbam to improve the performance metrics, namely mAP small and F1-score. Experimental results demonstrate that the enhanced model can effectively identify spinal tuberculosis lesions, with an mAP small of 0.9000, surpassing the original model’s 0.8340, and an F1-score of 0.9000, outperforming the original model’s 0.8657.